| Towards Reliable Medical LLMs: Benchmarking and Enhancing Confidence Estimation of Large Language Models in Medical ConsultationarXiv:2601.15645cs.CL | Zhiyao Ren, Yibing Zhan, Siyuan Liang +2 | — | 11 Sept 2026 | — | — | — | — |
| What Language is This? Ask Your TokenizerarXiv:2602.17655cs.CL | Clara Meister, Ahmetcan Yavuz, Pietro Lesci +1 | — | 11 Sept 2026 | — | — | — | — |
| Streaming Translation and Transcription Through Speech-to-Text Causal AlignmentarXiv:2603.11578cs.CL | Roman Koshkin, Jeon Haesung, Lianbo Liu +2 | — | 11 Sept 2026 | — | — | — | — |
| Evaluating LLM-Simulated Conversations in Modeling Inconsistent and Uncollaborative Behaviors in Human Social InteractionarXiv:2603.17094cs.CL | Ryo Kamoi, Ameya Godbole, Binglin Zhou +2 | — | 11 Sept 2026 | — | — | — | — |
| Alignment Reduces Expressed but Not Encoded Gender Bias: A Unified Framework and StudyarXiv:2603.24125cs.CL | Nour Bouchouchi, Thibault Laugel, Xavier Renard +2 | — | 11 Sept 2026 | — | — | — | — |
| Timing is Everything: Temporal Scaffolding of Semantic Surprise in HumorarXiv:2605.00143cs.CL | Yuxi Ma, Yongqian Peng, Junchen Lyu +2 | — | 11 Sept 2026 | — | — | — | — |
| A Recipe for Long-Context Reasoning in Large Language Models via On-Policy Optimization and DistillationarXiv:2605.12227cs.CL | Miguel Moura Ramos, Duarte M. Alves, Andr\'e F. T. Martins | — | 11 Sept 2026 | — | — | — | — |
| Cross-lingual brain-language model alignment is robust but challenges hierarchical and computational accountsarXiv:2605.21049cs.CL | Ni Yang, Rui He, Philipp Homan +2 | — | 11 Sept 2026 | — | — | — | — |
| MERIT: Matching Expertise via Rubric-Informed Training for Reviewer AssignmentarXiv:2605.27865cs.CL | Zixuan Yang, Yibo Zhao, Weicong Liu +1 | — | 11 Sept 2026 | — | — | — | — |
| Characterizing Narrative Content in Web-scale LLM Pretraining DataarXiv:2606.19468cs.CL | Teagan Johnson, Elliott Ash, Andrew Piper +1 | — | 11 Sept 2026 | — | — | — | — |
| Inverse Turing Bench: Evaluating Language Models as Judges of Human vs. AI DialoguearXiv:2606.21844cs.CL | William Hager, Ishika Rathi, Masum Hasan +1 | — | 11 Sept 2026 | — | — | — | — |
| A Factorial Study of Synthetic Data Generation for Low-Resource Machine Translation using Grammar BooksarXiv:2607.22376cs.CL | Varun Ghat Ravikumar, Sina Ahmadi, Lena J\"ager +1 | — | 11 Sept 2026 | — | — | — | — |
| Predicting Startup Exit from Textual Descriptors - A Computational Linguistics FrameworkarXiv:2608.00045cs.CL | Alberto M. G. Saruggia, Sebastien Germano | — | 11 Sept 2026 | — | — | — | — |
| Causal Episodic Memory for Feedback-Driven Agent RepairarXiv:2608.05906cs.CL | Khang Nhat Hoang Vo, Tam Minh Chu, Anh Trac Duc Dinh +2 | — | 11 Sept 2026 | — | — | — | — |
| VectraYX-Vision-1B: A Sub-2B Spanish/LATAM Cybersecurity Vision-Language Model with Structured Visual Reasoning and Native Tool UsearXiv:2608.08477cs.CL | Juan S. Santillana | — | 11 Sept 2026 | — | — | — | — |
| Self-Evolving Embodied Agents via Skill-Harness EvolutionarXiv:2608.11350cs.CL | Peidong Wang, Zhiming Ma, Ying Chang +2 | — | 11 Sept 2026 | — | — | — | — |
| Unadapted Multilingual ASR on a Garrusi Kurdish Evaluation Set: A Common-Reference Staged Normalization AnalysisarXiv:2608.16379cs.CL | Hiwa Asadpour | — | 11 Sept 2026 | — | — | — | — |
| Whitewashing Hate, Smearing Harmless Content: Annotator-Style Rebuttal Attacks on LLM-Based ModerationarXiv:2608.22230cs.CL | Junyu Lu, Kaiyuan Liu, Kaichun Wang +2 | — | 11 Sept 2026 | — | — | — | — |
| DelistBench: Evaluating Search-Enabled LLMs for Auditable Corporate-Event Database CompletionarXiv:2608.22770cs.CL | Xuan Yao, Shuping Li, Yang Dai +2 | — | 11 Sept 2026 | — | — | — | — |
| Toward a Cross-Lingual Romanization Ecosystem for Sinitic Languages: A Paired Mandarin-Cantonese Case StudyarXiv:2608.29170cs.CL | Zijie Zhang, Tan Lee, Yong Cao +1 | — | 11 Sept 2026 | — | — | — | — |
| Quit While You're Ahead: Quit for Efficient Candidate Generation in Machine Translation RerankingarXiv:2609.00588cs.CL | Guangyu Chen, Boxuan Lyu, Hidetaka Kamigaito +2 | — | 11 Sept 2026 | — | — | — | — |
| OUTLETS: Output-Length Prediction from Speculative Decoding BackbonesarXiv:2609.01068cs.CL | Weihuang Wen, Yingying Liu, Yichuan Liu +2 | — | 11 Sept 2026 | — | — | — | — |
| Cache-Aware Joint Router Adaptation for Memory-Efficient MoE InferencearXiv:2609.04895cs.CL | Zhenhe Wu, Yaping Jin, Qinghua Xing +2 | — | 11 Sept 2026 | — | — | — | — |
| CARRE: Counterfactual Action Retrieval and Reason Evaluation for Explainable Churn PrescriptionarXiv:2609.09766cs.CL | Minjoo Kim, Sangjin Park, Seung Hwan Cho | — | 11 Sept 2026 | — | — | — | — |
| SalamandraTA at WMT 2026 Terminology Shared Task: Hard Examples Are Better TeachersarXiv:2609.09999cs.CL | Xixian Liao, Maite Melero | — | 11 Sept 2026 | — | — | — | — |